enhanced-mcp-memory and memory-mcp
About enhanced-mcp-memory
cbunting99/enhanced-mcp-memory
An enhanced MCP (Model Context Protocol) server for intelligent memory and task management, designed for AI assistants and development workflows. Features semantic search, automatic task extraction, knowledge graphs, and comprehensive project management.
Implements a 5-stage sequential thinking engine with token optimization (30-70% compression) and automatic context summarization for conversation continuity, built on FastMCP with SQLite persistence. Automatically detects project conventions (OS, package managers, build tools, runtime types) and learns command patterns to correct AI suggestions—particularly useful for cross-platform development. Exposes 20+ MCP tools including thinking chains, task decomposition, and knowledge graph relationships that link memories to code file paths.
About memory-mcp
JamesANZ/memory-mcp
A simple MCP server that stores and retrieves memories from multiple LLMs.
Implements intelligent context window caching with automatic archival at 80% capacity and retrieval when usage drops below 30%, using MongoDB for persistent storage and relevance scoring via keyword overlap. Provides tag-based search and conversation summaries to manage extended LLM sessions, integrating directly with Cursor and Claude Desktop via the MCP protocol.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work